In [1]:
import samplerate
from tensorflow import keras
from keras import losses
from keras.callbacks import EarlyStopping
from keras.optimizers import adam


import os
import sys
os.environ["CUDA_VISIBLE_DEVICES"]="4"
sys.path.insert(1,'/home/jgozlan/GIT/scripts/')
sys.path.insert(1,'/home/jgozlan/GIT/models/')
sys.path.insert(1, '/home/jgozlan/GIT/models_analysis/')
import tensorflow as tf
tf.test.is_gpu_available()

Using TensorFlow backend.
Out[1]:
True
In [2]:
import matplotlib.pyplot as plt
In [3]:
from imu_extractor import get_all_dataframes_for_forecasting, get_freq_magn, transform_dataset_into_freq_magn
from train_test_split import get_train_test_split
from baseline import find_frequency,repeat_period_forecast_acf, get_mean_line_forecast, get_flat_line_forecast
from metrics import compare_method, plot_few_prediction
from models import create_lstm_encoder_decoder
In [4]:
path_cluster0 = ['Run_Features']

path_cluster1 = ['CarDriving_Features']

path_cluster2 = ['Karting_Features',
                 'MotorcycleHelmet_Features',
                 'Scooter_Features','SkateboardChesty_Features',
                 'SnowboardSeeker_Features','Hiking_Features']

path_all_classes = path_cluster0 + path_cluster1 + path_cluster2

recording_freq = 6400.0
downsampling_freq = 200.0

all_dfs_classes = []

for i,c in enumerate(path_cluster0):
    dfs = get_all_dataframes_for_forecasting("Database/" + c, recording_freq, downsampling_freq)
    all_dfs_classes.append(dfs)
    
all_df = [item for sublist in all_dfs_classes for item in sublist]

GH010029.MP4.eis_dump.bin_features.json
GH010011.MP4.eis_dump.bin_features.json
GH019983.MP4.eis_dump.bin_features.json
GH010019.MP4.eis_dump.bin_features.json
GH010030.MP4.eis_dump.bin_features.json
GH010028.MP4.eis_dump.bin_features.json
GH019982.MP4.eis_dump.bin_features.json
GH010012.MP4.eis_dump.bin_features.json
GH019973.MP4.eis_dump.bin_features.json
In [6]:
lag = 500
ahead = 100
delay = 1
test_size = 0.2
dim = 12
target_index = [0,1,2]
classification = False

X_train, y_train, X_test, y_test = get_train_test_split(all_df, test_size, lag, ahead, delay, target_index, classification = False)
In [7]:
num_freq = 12

transformed_X_train = transform_dataset_into_freq_magn(X_train, downsampling_freq, num_freq)
transformed_X_test = transform_dataset_into_freq_magn(X_test, downsampling_freq, num_freq)

freq_dim_in = transformed_X_train.shape[1]
In [27]:
freq_dim_in
Out[27]:
288
In [8]:
import pickle
from numpy import unique
from numpy import where
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
import matplotlib.pyplot as plt
import pickle

cluster_classification_model = keras.models.load_model('models_analysis/cluster4_classification_model_new')

running_forecasting_model = keras.models.load_model('models_analysis/running_forecasting_multi_step1')

lda_model = pickle.load(open('models_analysis/lda_model_time.sav', 'rb'))
kmeans_model = pickle.load(open('models_analysis/kmeans_model_time.sav', 'rb'))
gmm_model = pickle.load(open('models_analysis/gmm_model.sav', 'rb'))

WARNING:tensorflow:From /home/jgozlan/.conda/envs/base_cvdev_jeremygoz/lib/python3.7/site-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
In [9]:
X_train.shape, X_test.shape, transformed_X_train.shape, transformed_X_test.shape
Out[9]:
((79012, 500, 12), (17050, 500, 12), (79012, 288), (17050, 288))
In [10]:
forecast = running_forecasting_model.predict(X_test)

forecast_x = forecast[:,:,0].reshape((forecast.shape[0],forecast.shape[1]))
forecast_y = forecast[:,:,1].reshape((forecast.shape[0],forecast.shape[1]))
forecast_z = forecast[:,:,2].reshape((forecast.shape[0],forecast.shape[1]))
In [11]:
import random
import numpy as np
from evaluation2 import plot_forecasts2, plot_metrics, get_metrics_for_forecast
import matplotlib.pyplot as plt
In [144]:
mae_threshold_x_l = np.zeros((100,ahead))
mae_threshold_y_l = np.zeros((100,ahead))
mae_threshold_z_l = np.zeros((100,ahead))

mse_threshold_x_l = np.zeros((100,ahead))
mse_threshold_y_l = np.zeros((100,ahead))
mse_threshold_z_l = np.zeros((100,ahead))

mae_threshold_x_h = np.zeros((100,ahead))
mae_threshold_y_h = np.zeros((100,ahead))
mae_threshold_z_h = np.zeros((100,ahead))

mse_threshold_x_h = np.zeros((100,ahead))
mse_threshold_y_h = np.zeros((100,ahead))
mse_threshold_z_h = np.zeros((100,ahead))

mae_x_g = np.zeros((1,ahead))
mae_y_g = np.zeros((1,ahead))
mae_z_g = np.zeros((1,ahead))

mse_x_g = np.zeros((1,ahead))
mse_y_g = np.zeros((1,ahead))
mse_z_g = np.zeros((1,ahead))

cluster_probs = cluster_classification_model.predict(transformed_X_test)
cluster0_probs = cluster_probs[:,0]

mae_x, mse_x, mape_x, smape_x = get_metrics_for_forecast(y_test[:,:,0].reshape((-1,ahead)), forecast_x)
mae_y, mse_y, mape_y, smape_y = get_metrics_for_forecast(y_test[:,:,1].reshape((-1,ahead)), forecast_y)
mae_z, mse_z, mape_z, smape_z = get_metrics_for_forecast(y_test[:,:,2].reshape((-1,ahead)), forecast_z)
    
mae_x_g = mae_x
mae_y_g = mae_y
mae_z_g = mae_z

mse_x_g = mse_x
mse_y_g = mse_y
mse_z_g = mse_z


for threshold in range(0,100,1):

    prob_threshold = threshold/100.0

    idx_lower = np.where(cluster0_probs < prob_threshold)[0]
    idx_higher = np.where(cluster0_probs > prob_threshold)[0]
    print(prob_threshold, len(idx_lower), len(idx_higher))
    
    if len(idx_lower) > 0:

        mae_low_x, mse_low_x, mape_low_x, smape_low_x = get_metrics_for_forecast(y_test[idx_lower,:,0].reshape((-1,ahead)), forecast_x[idx_lower])
        mae_low_y, mse_low_y, mape_low_y, smape_low_y = get_metrics_for_forecast(y_test[idx_lower,:,1].reshape((-1,ahead)), forecast_y[idx_lower])
        mae_low_z, mse_low_z, mape_low_z, smape_low_z = get_metrics_for_forecast(y_test[idx_lower,:,2].reshape((-1,ahead)), forecast_z[idx_lower])
        
        mae_threshold_x_l[threshold] = mae_low_x
        mae_threshold_y_l[threshold] = mae_low_y
        mae_threshold_z_l[threshold] = mae_low_z

        mse_threshold_x_l[threshold] = mse_low_x
        mse_threshold_y_l[threshold] = mse_low_y
        mse_threshold_z_l[threshold] = mse_low_z
    
    if len(idx_higher) > 0:
        mae_high_x, mse_high_x, mape_high_x, smape_high_x = get_metrics_for_forecast(y_test[idx_higher,:,0].reshape((-1,ahead)), forecast_x[idx_higher])
        mae_high_y, mse_high_y, mape_high_y, smape_high_y = get_metrics_for_forecast(y_test[idx_higher,:,1].reshape((-1,ahead)), forecast_y[idx_higher])
        mae_high_z, mse_high_z, mape_high_z, smape_high_z = get_metrics_for_forecast(y_test[idx_higher,:,2].reshape((-1,ahead)), forecast_z[idx_higher])
    
        mae_threshold_x_h[threshold] = mae_high_x
        mae_threshold_y_h[threshold] = mae_high_y
        mae_threshold_z_h[threshold] = mae_high_z

        mse_threshold_x_h[threshold] = mse_high_x
        mse_threshold_y_h[threshold] = mse_high_y
        mse_threshold_z_h[threshold] = mse_high_z

0.0 0 17050
0.01 3 17047
0.02 4 17046
0.03 5 17045
0.04 7 17043
0.05 7 17043
0.06 7 17043
0.07 7 17043
0.08 7 17043
0.09 8 17042
0.1 8 17042
0.11 8 17042
0.12 8 17042
0.13 8 17042
0.14 8 17042
0.15 8 17042
0.16 8 17042
0.17 8 17042
0.18 8 17042
0.19 8 17042
0.2 8 17042
0.21 8 17042
0.22 8 17042
0.23 8 17042
0.24 9 17041
0.25 9 17041
0.26 9 17041
0.27 9 17041
0.28 9 17041
0.29 9 17041
0.3 9 17041
0.31 9 17041
0.32 9 17041
0.33 9 17041
0.34 9 17041
0.35 9 17041
0.36 9 17041
0.37 9 17041
0.38 9 17041
0.39 10 17040
0.4 10 17040
0.41 10 17040
0.42 10 17040
0.43 10 17040
0.44 10 17040
0.45 10 17040
0.46 10 17040
0.47 10 17040
0.48 10 17040
0.49 10 17040
0.5 10 17040
0.51 10 17040
0.52 10 17040
0.53 10 17040
0.54 10 17040
0.55 10 17040
0.56 11 17039
0.57 11 17039
0.58 11 17039
0.59 11 17039
0.6 11 17039
0.61 11 17039
0.62 11 17039
0.63 11 17039
0.64 11 17039
0.65 11 17039
0.66 11 17039
0.67 11 17039
0.68 11 17039
0.69 11 17039
0.7 11 17039
0.71 11 17039
0.72 11 17039
0.73 11 17039
0.74 11 17039
0.75 11 17039
0.76 11 17039
0.77 11 17039
0.78 11 17039
0.79 11 17039
0.8 11 17039
0.81 11 17039
0.82 11 17039
0.83 11 17039
0.84 11 17039
0.85 11 17039
0.86 11 17039
0.87 12 17038
0.88 13 17037
0.89 13 17037
0.9 13 17037
0.91 13 17037
0.92 13 17037
0.93 13 17037
0.94 13 17037
0.95 14 17036
0.96 14 17036
0.97 14 17036
0.98 14 17036
0.99 18 17032
In [12]:
def plot_metrics_for_threshold(metrics_threshold, metrics_global):
    
    fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18,4))

    for i, ax in enumerate(axs.flatten()):  
        ax.plot(range(ahead), metrics_global[i], label = "global")
        for threshold in range(90,100,1):
            ax.plot(range(ahead), metrics_threshold[i][threshold], label = threshold)
        ax.legend(loc="upper left")

    plt.show()
In [146]:
plot_metrics_for_threshold([mae_threshold_x_l,mae_threshold_y_l,mae_threshold_z_l], [mae_x_g, mae_y_g, mae_z_g])
In [147]:
plot_metrics_for_threshold([mse_threshold_x_l,mse_threshold_y_l,mse_threshold_z_l],[mse_x_g, mse_y_g, mse_z_g])
In [148]:
plot_metrics_for_threshold([mae_threshold_x_h,mae_threshold_y_h,mae_threshold_z_h], [mae_x_g, mae_y_g, mae_z_g])
In [149]:
plot_metrics_for_threshold([mse_threshold_x_h,mse_threshold_y_h,mse_threshold_z_h], [mse_x_g, mse_y_g, mse_z_g])
In [150]:
import numpy as np

batch_pipeline_size = 100
threshold  = 0.7

predictions_cluster = np.zeros((X_test.shape[0], ahead, 1 ))
predictions_global = np.zeros((X_test.shape[0], ahead, 1 ))
bad_indexes = np.zeros((X_test.shape[0]))


for i in range(0, len(X_test), batch_pipeline_size):
    
    if (i % 5000) == 0:
        print(i)

    batch_time = X_test[i: (i+ batch_pipeline_size)]
    batch_freq = transformed_X_test[i: (i+ batch_pipeline_size)]

    cluster_probs = cluster_classification_model.predict(batch_freq)
    cluster0_probs = cluster_probs[:,0]
    idx = np.where(cluster0_probs < threshold)[0]
    bad_indexes[i + idx] = 1


    
    

0
5000
10000
15000
In [13]:
import random
from evaluation2 import plot_forecasts2, plot_metrics
import matplotlib.pyplot as plt

def plot_examples_test(indexes, X_true, Y_true, forecast, k):
    
    random_indexes = random.sample(indexes, k)
    
    for i in random_indexes:
        
        fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18,4))
        
        x_input = X_true[i][:,0].reshape((lag,-1))
        y_input = X_true[i][:,1].reshape((lag,-1))
        z_input = X_true[i][:,2].reshape((lag,-1))

        x_true = Y_true[i][:,0].reshape((ahead,-1))
        y_true = Y_true[i][:,1].reshape((ahead,-1))
        z_true = Y_true[i][:,2].reshape((ahead,-1))

        x_forecast = forecast[i][:,0].reshape((ahead,-1))
        y_forecast = forecast[i][:,1].reshape((ahead,-1))
        z_forecast = forecast[i][:,2].reshape((ahead,-1))

        t = [len(x_input) + j for j in range(len(x_true))]
        #print(t)

        inputs = [x_input, y_input,z_input]
        outputs = [x_true , y_true , z_true]
        forecasts = [x_forecast, y_forecast, z_forecast]

        signal_labels = ['x_gyro signal', 'y_gyro_input signal','z_gyro signal']
        signal_colors = ['red','green','blue']

        forecast_labels = ['x_gyro forecast', 'y_gyro forecast','z_gyro forecast']
        forecast_colors = ['orange','lime','cyan']
        

        for i, ax in enumerate(axs.flatten()):
            ax.plot(range(len(inputs[i])), inputs[i], label = signal_labels[i], color = signal_colors[i])
            ax.plot(t, outputs[i], color = signal_colors[i])
            ax.plot(t, forecasts[i], label = forecast_labels[i], color = forecast_colors[i])
            ax.legend(loc="upper left")
        

        plt.show()
In [153]:
k = 10
plot_examples_test(list(np.where(bad_indexes==0)[0]), X_test, y_test, forecast, k)
In [154]:
k = 10
plot_examples_test(list(np.where(bad_indexes==1)[0]), X_test, y_test, forecast, k)
In [14]:
transformed_X_test  = X_test.reshape((-1,X_test.shape[1]*X_test.shape[2]))
X_random_lda3 = lda_model.transform(transformed_X_test)
from sklearn.metrics.pairwise import euclidean_distances
In [22]:
mae_threshold_x_l = np.zeros((100,ahead))
mae_threshold_y_l = np.zeros((100,ahead))
mae_threshold_z_l = np.zeros((100,ahead))

mse_threshold_x_l = np.zeros((100,ahead))
mse_threshold_y_l = np.zeros((100,ahead))
mse_threshold_z_l = np.zeros((100,ahead))

mae_threshold_x_h = np.zeros((100,ahead))
mae_threshold_y_h = np.zeros((100,ahead))
mae_threshold_z_h = np.zeros((100,ahead))

mse_threshold_x_h = np.zeros((100,ahead))
mse_threshold_y_h = np.zeros((100,ahead))
mse_threshold_z_h = np.zeros((100,ahead))

mae_x_g = np.zeros((1,ahead))
mae_y_g = np.zeros((1,ahead))
mae_z_g = np.zeros((1,ahead))

mse_x_g = np.zeros((1,ahead))
mse_y_g = np.zeros((1,ahead))
mse_z_g = np.zeros((1,ahead))

cluster_center = kmeans_model.cluster_centers_[-1]
distances_centroid_run = euclidean_distances(X_random_lda3, [cluster_center])

mae_x, mse_x, mape_x, smape_x = get_metrics_for_forecast(y_test[:,:,0].reshape((-1,ahead)), forecast_x)
mae_y, mse_y, mape_y, smape_y = get_metrics_for_forecast(y_test[:,:,1].reshape((-1,ahead)), forecast_y)
mae_z, mse_z, mape_z, smape_z = get_metrics_for_forecast(y_test[:,:,2].reshape((-1,ahead)), forecast_z)
    
mae_x_g = mae_x
mae_y_g = mae_y
mae_z_g = mae_z

mse_x_g = mse_x
mse_y_g = mse_y
mse_z_g = mse_z


for threshold in range(5,100,1):

    current_threshold = threshold/10.0

    idx_lower = np.where(distances_centroid_run < current_threshold)[0]
    idx_higher = np.where(distances_centroid_run > current_threshold)[0]

    #print(current_threshold, len(idx_lower), len(idx_higher))
    
    if len(idx_lower) > 0:

        mae_low_x, mse_low_x, mape_low_x, smape_low_x = get_metrics_for_forecast(y_test[idx_lower,:,0].reshape((-1,ahead)), forecast_x[idx_lower])
        mae_low_y, mse_low_y, mape_low_y, smape_low_y = get_metrics_for_forecast(y_test[idx_lower,:,1].reshape((-1,ahead)), forecast_y[idx_lower])
        mae_low_z, mse_low_z, mape_low_z, smape_low_z = get_metrics_for_forecast(y_test[idx_lower,:,2].reshape((-1,ahead)), forecast_z[idx_lower])
        
        mae_threshold_x_l[threshold] = mae_low_x
        mae_threshold_y_l[threshold] = mae_low_y
        mae_threshold_z_l[threshold] = mae_low_z

        mse_threshold_x_l[threshold] = mse_low_x
        mse_threshold_y_l[threshold] = mse_low_y
        mse_threshold_z_l[threshold] = mse_low_z
    
    if len(idx_higher) > 0:
        mae_high_x, mse_high_x, mape_high_x, smape_high_x = get_metrics_for_forecast(y_test[idx_higher,:,0].reshape((-1,ahead)), forecast_x[idx_higher])
        mae_high_y, mse_high_y, mape_high_y, smape_high_y = get_metrics_for_forecast(y_test[idx_higher,:,1].reshape((-1,ahead)), forecast_y[idx_higher])
        mae_high_z, mse_high_z, mape_high_z, smape_high_z = get_metrics_for_forecast(y_test[idx_higher,:,2].reshape((-1,ahead)), forecast_z[idx_higher])
    
        mae_threshold_x_h[threshold] = mae_high_x
        mae_threshold_y_h[threshold] = mae_high_y
        mae_threshold_z_h[threshold] = mae_high_z

        mse_threshold_x_h[threshold] = mse_high_x
        mse_threshold_y_h[threshold] = mse_high_y
        mse_threshold_z_h[threshold] = mse_high_z

    print("THRESHOLD", current_threshold, len(idx_lower), len(idx_higher))

THRESHOLD 0.5 23 17027
THRESHOLD 0.6 31 17019
THRESHOLD 0.7 51 16999
THRESHOLD 0.8 89 16961
THRESHOLD 0.9 125 16925
THRESHOLD 1.0 177 16873
THRESHOLD 1.1 229 16821
THRESHOLD 1.2 302 16748
THRESHOLD 1.3 404 16646
THRESHOLD 1.4 485 16565
THRESHOLD 1.5 598 16452
THRESHOLD 1.6 726 16324
THRESHOLD 1.7 878 16172
THRESHOLD 1.8 1040 16010
THRESHOLD 1.9 1204 15846
THRESHOLD 2.0 1416 15634
THRESHOLD 2.1 1656 15394
THRESHOLD 2.2 1917 15133
THRESHOLD 2.3 2199 14851
THRESHOLD 2.4 2524 14526
THRESHOLD 2.5 2871 14179
THRESHOLD 2.6 3231 13819
THRESHOLD 2.7 3580 13470
THRESHOLD 2.8 4037 13013
THRESHOLD 2.9 4487 12563
THRESHOLD 3.0 4944 12106
THRESHOLD 3.1 5486 11564
THRESHOLD 3.2 6026 11024
THRESHOLD 3.3 6511 10539
THRESHOLD 3.4 7010 10040
THRESHOLD 3.5 7539 9511
THRESHOLD 3.6 8025 9025
THRESHOLD 3.7 8511 8539
THRESHOLD 3.8 8975 8075
THRESHOLD 3.9 9402 7648
THRESHOLD 4.0 9851 7199
THRESHOLD 4.1 10219 6831
THRESHOLD 4.2 10600 6450
THRESHOLD 4.3 10937 6113
THRESHOLD 4.4 11269 5781
THRESHOLD 4.5 11540 5510
THRESHOLD 4.6 11792 5258
THRESHOLD 4.7 12056 4994
THRESHOLD 4.8 12287 4763
THRESHOLD 4.9 12513 4537
THRESHOLD 5.0 12723 4327
THRESHOLD 5.1 12903 4147
THRESHOLD 5.2 13091 3959
THRESHOLD 5.3 13264 3786
THRESHOLD 5.4 13423 3627
THRESHOLD 5.5 13569 3481
THRESHOLD 5.6 13729 3321
THRESHOLD 5.7 13861 3189
THRESHOLD 5.8 13989 3061
THRESHOLD 5.9 14121 2929
THRESHOLD 6.0 14237 2813
THRESHOLD 6.1 14341 2709
THRESHOLD 6.2 14449 2601
THRESHOLD 6.3 14561 2489
THRESHOLD 6.4 14671 2379
THRESHOLD 6.5 14757 2293
THRESHOLD 6.6 14849 2201
THRESHOLD 6.7 14945 2105
THRESHOLD 6.8 15043 2007
THRESHOLD 6.9 15130 1920
THRESHOLD 7.0 15200 1850
THRESHOLD 7.1 15278 1772
THRESHOLD 7.2 15347 1703
THRESHOLD 7.3 15413 1637
THRESHOLD 7.4 15471 1579
THRESHOLD 7.5 15537 1513
THRESHOLD 7.6 15596 1454
THRESHOLD 7.7 15662 1388
THRESHOLD 7.8 15710 1340
THRESHOLD 7.9 15750 1300
THRESHOLD 8.0 15801 1249
THRESHOLD 8.1 15860 1190
THRESHOLD 8.2 15897 1153
THRESHOLD 8.3 15947 1103
THRESHOLD 8.4 15994 1056
THRESHOLD 8.5 16035 1015
THRESHOLD 8.6 16078 972
THRESHOLD 8.7 16107 943
THRESHOLD 8.8 16146 904
THRESHOLD 8.9 16182 868
THRESHOLD 9.0 16208 842
THRESHOLD 9.1 16248 802
THRESHOLD 9.2 16277 773
THRESHOLD 9.3 16310 740
THRESHOLD 9.4 16333 717
THRESHOLD 9.5 16351 699
THRESHOLD 9.6 16377 673
THRESHOLD 9.7 16406 644
THRESHOLD 9.8 16426 624
THRESHOLD 9.9 16444 606
In [23]:
mae_x = [mae_threshold_x_l, mae_threshold_x_h]
mae_y = [mae_threshold_y_l, mae_threshold_y_h]
mae_z = [mae_threshold_z_l, mae_threshold_z_h]

fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18,4))

for i, ax in enumerate(axs.flatten()): 
    if i == 0:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_x[0], axis = 1), label = "X- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_x[1], axis = 1), label = "X- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_x_g), label = "X- global")
    elif i == 1:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_y[0], axis = 1), label = "Y- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_y[1], axis = 1), label = "Y- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_y_g), label = "Y - global")
    else:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_z[0], axis = 1), label = "Z- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_z[1], axis = 1), label = "Z- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_z_g), label = "Z - global")

    ax.legend(loc="lower left")

plt.show()
In [24]:
def plot_metrics_for_euc_threshold(metrics_threshold, metrics_global):
    
    fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18,4))

    for i, ax in enumerate(axs.flatten()):  
        ax.plot(range(ahead), metrics_global[i], label = "global", color='black')
        for threshold in range(5,80,5):
            ax.plot(range(ahead), metrics_threshold[i][threshold], label = threshold)
        ax.legend(loc="upper left")

    plt.show()
In [25]:
# LOWER THE BETTER
plot_metrics_for_euc_threshold([mae_threshold_x_l,mae_threshold_y_l,mae_threshold_z_l], [mae_x_g, mae_y_g, mae_z_g])
In [160]:
#HIGHER THE BETTER
plot_metrics_for_euc_threshold([mae_threshold_x_h,mae_threshold_y_h,mae_threshold_z_h], [mae_x_g, mae_y_g, mae_z_g])
In [27]:
threshold  = 9.9
bad_indexes = np.zeros((X_test.shape[0]))

idx_lower = np.where(distances_centroid_run < threshold)[0]
idx_higher = np.where(distances_centroid_run > threshold)[0]

bad_indexes[idx_higher] = 1
k = 20
plot_examples_test(list(np.where(bad_indexes==1)[0]), X_test, y_test, forecast, k)
In [21]:
threshold  = 8
bad_indexes = np.zeros((X_test.shape[0]))

idx_lower = np.where(distances_centroid_run < threshold)[0]
idx_higher = np.where(distances_centroid_run > threshold)[0]

bad_indexes[idx_higher] = 1

k = 20
plot_examples_test(list(np.where(bad_indexes==1)[0]), X_test, y_test, forecast, k)
In [ ]:
# GMMMMMMMMMMMMMMMM
In [163]:
mae_threshold_x_l = np.zeros((100,ahead))
mae_threshold_y_l = np.zeros((100,ahead))
mae_threshold_z_l = np.zeros((100,ahead))

mse_threshold_x_l = np.zeros((100,ahead))
mse_threshold_y_l = np.zeros((100,ahead))
mse_threshold_z_l = np.zeros((100,ahead))

mae_threshold_x_h = np.zeros((100,ahead))
mae_threshold_y_h = np.zeros((100,ahead))
mae_threshold_z_h = np.zeros((100,ahead))

mse_threshold_x_h = np.zeros((100,ahead))
mse_threshold_y_h = np.zeros((100,ahead))
mse_threshold_z_h = np.zeros((100,ahead))

mae_x_g = np.zeros((1,ahead))
mae_y_g = np.zeros((1,ahead))
mae_z_g = np.zeros((1,ahead))

mse_x_g = np.zeros((1,ahead))
mse_y_g = np.zeros((1,ahead))
mse_z_g = np.zeros((1,ahead))

cluster_center = gmm_model.means_[0]
distances_centroid_run = euclidean_distances(X_random_lda3, [cluster_center])

mae_x, mse_x, mape_x, smape_x = get_metrics_for_forecast(y_test[:,:,0].reshape((-1,ahead)), forecast_x)
mae_y, mse_y, mape_y, smape_y = get_metrics_for_forecast(y_test[:,:,1].reshape((-1,ahead)), forecast_y)
mae_z, mse_z, mape_z, smape_z = get_metrics_for_forecast(y_test[:,:,2].reshape((-1,ahead)), forecast_z)
    
mae_x_g = mae_x
mae_y_g = mae_y
mae_z_g = mae_z

mse_x_g = mse_x
mse_y_g = mse_y
mse_z_g = mse_z


for threshold in range(0,100,1):

    current_threshold = threshold/10.0

    idx_lower = np.where(distances_centroid_run < current_threshold)[0]
    idx_higher = np.where(distances_centroid_run > current_threshold)[0]

    #print(current_threshold, len(idx_lower), len(idx_higher))
    
    if len(idx_lower) > 0:

        mae_low_x, mse_low_x, mape_low_x, smape_low_x = get_metrics_for_forecast(y_test[idx_lower,:,0].reshape((-1,ahead)), forecast_x[idx_lower])
        mae_low_y, mse_low_y, mape_low_y, smape_low_y = get_metrics_for_forecast(y_test[idx_lower,:,1].reshape((-1,ahead)), forecast_y[idx_lower])
        mae_low_z, mse_low_z, mape_low_z, smape_low_z = get_metrics_for_forecast(y_test[idx_lower,:,2].reshape((-1,ahead)), forecast_z[idx_lower])
        
        mae_threshold_x_l[threshold] = mae_low_x
        mae_threshold_y_l[threshold] = mae_low_y
        mae_threshold_z_l[threshold] = mae_low_z

        mse_threshold_x_l[threshold] = mse_low_x
        mse_threshold_y_l[threshold] = mse_low_y
        mse_threshold_z_l[threshold] = mse_low_z
    
    if len(idx_higher) > 0:
        mae_high_x, mse_high_x, mape_high_x, smape_high_x = get_metrics_for_forecast(y_test[idx_higher,:,0].reshape((-1,ahead)), forecast_x[idx_higher])
        mae_high_y, mse_high_y, mape_high_y, smape_high_y = get_metrics_for_forecast(y_test[idx_higher,:,1].reshape((-1,ahead)), forecast_y[idx_higher])
        mae_high_z, mse_high_z, mape_high_z, smape_high_z = get_metrics_for_forecast(y_test[idx_higher,:,2].reshape((-1,ahead)), forecast_z[idx_higher])
    
        mae_threshold_x_h[threshold] = mae_high_x
        mae_threshold_y_h[threshold] = mae_high_y
        mae_threshold_z_h[threshold] = mae_high_z

        mse_threshold_x_h[threshold] = mse_high_x
        mse_threshold_y_h[threshold] = mse_high_y
        mse_threshold_z_h[threshold] = mse_high_z

    print("THRESHOLD", current_threshold, len(idx_lower), len(idx_higher))

THRESHOLD 0.0 0 17050
THRESHOLD 0.1 0 17050
THRESHOLD 0.2 0 17050
THRESHOLD 0.3 0 17050
THRESHOLD 0.4 0 17050
THRESHOLD 0.5 1 17049
THRESHOLD 0.6 3 17047
THRESHOLD 0.7 12 17038
THRESHOLD 0.8 27 17023
THRESHOLD 0.9 35 17015
THRESHOLD 1.0 55 16995
THRESHOLD 1.1 79 16971
THRESHOLD 1.2 113 16937
THRESHOLD 1.3 152 16898
THRESHOLD 1.4 189 16861
THRESHOLD 1.5 234 16816
THRESHOLD 1.6 264 16786
THRESHOLD 1.7 320 16730
THRESHOLD 1.8 395 16655
THRESHOLD 1.9 502 16548
THRESHOLD 2.0 622 16428
THRESHOLD 2.1 737 16313
THRESHOLD 2.2 850 16200
THRESHOLD 2.3 959 16091
THRESHOLD 2.4 1091 15959
THRESHOLD 2.5 1239 15811
THRESHOLD 2.6 1388 15662
THRESHOLD 2.7 1542 15508
THRESHOLD 2.8 1704 15346
THRESHOLD 2.9 1882 15168
THRESHOLD 3.0 2077 14973
THRESHOLD 3.1 2290 14760
THRESHOLD 3.2 2536 14514
THRESHOLD 3.3 2820 14230
THRESHOLD 3.4 3148 13902
THRESHOLD 3.5 3516 13534
THRESHOLD 3.6 3905 13145
THRESHOLD 3.7 4308 12742
THRESHOLD 3.8 4767 12283
THRESHOLD 3.9 5240 11810
THRESHOLD 4.0 5753 11297
THRESHOLD 4.1 6208 10842
THRESHOLD 4.2 6736 10314
THRESHOLD 4.3 7234 9816
THRESHOLD 4.4 7704 9346
THRESHOLD 4.5 8247 8803
THRESHOLD 4.6 8803 8247
THRESHOLD 4.7 9359 7691
THRESHOLD 4.8 9895 7155
THRESHOLD 4.9 10441 6609
THRESHOLD 5.0 10945 6105
THRESHOLD 5.1 11458 5592
THRESHOLD 5.2 11957 5093
THRESHOLD 5.3 12405 4645
THRESHOLD 5.4 12795 4255
THRESHOLD 5.5 13167 3883
THRESHOLD 5.6 13455 3595
THRESHOLD 5.7 13769 3281
THRESHOLD 5.8 14104 2946
THRESHOLD 5.9 14370 2680
THRESHOLD 6.0 14603 2447
THRESHOLD 6.1 14852 2198
THRESHOLD 6.2 15042 2008
THRESHOLD 6.3 15214 1836
THRESHOLD 6.4 15378 1672
THRESHOLD 6.5 15490 1560
THRESHOLD 6.6 15611 1439
THRESHOLD 6.7 15756 1294
THRESHOLD 6.8 15857 1193
THRESHOLD 6.9 15956 1094
THRESHOLD 7.0 16042 1008
THRESHOLD 7.1 16129 921
THRESHOLD 7.2 16228 822
THRESHOLD 7.3 16310 740
THRESHOLD 7.4 16400 650
THRESHOLD 7.5 16490 560
THRESHOLD 7.6 16580 470
THRESHOLD 7.7 16641 409
THRESHOLD 7.8 16733 317
THRESHOLD 7.9 16801 249
THRESHOLD 8.0 16876 174
THRESHOLD 8.1 16947 103
THRESHOLD 8.2 16987 63
THRESHOLD 8.3 17013 37
THRESHOLD 8.4 17028 22
THRESHOLD 8.5 17040 10
THRESHOLD 8.6 17045 5
THRESHOLD 8.7 17046 4
THRESHOLD 8.8 17049 1
THRESHOLD 8.9 17050 0
THRESHOLD 9.0 17050 0
THRESHOLD 9.1 17050 0
THRESHOLD 9.2 17050 0
THRESHOLD 9.3 17050 0
THRESHOLD 9.4 17050 0
THRESHOLD 9.5 17050 0
THRESHOLD 9.6 17050 0
THRESHOLD 9.7 17050 0
THRESHOLD 9.8 17050 0
THRESHOLD 9.9 17050 0
In [164]:
mae_x = [mae_threshold_x_l, mae_threshold_x_h]
mae_y = [mae_threshold_y_l, mae_threshold_y_h]
mae_z = [mae_threshold_z_l, mae_threshold_z_h]

fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18,4))

for i, ax in enumerate(axs.flatten()): 
    if i == 0:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_x[0], axis = 1), label = "X- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_x[1], axis = 1), label = "X- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_x_g), label = "X- global")
    elif i == 1:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_y[0], axis = 1), label = "Y- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_y[1], axis = 1), label = "Y- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_y_g), label = "Y - global")
    else:
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_z[0], axis = 1), label = "Z- under threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.mean(mae_z[1], axis = 1), label = "Z- above threshold")
        ax.plot(np.arange(0.0,10.0,0.1), np.ones((100))* np.mean(mae_z_g), label = "Z - global")

    ax.legend(loc="lower left")

plt.show()